Enhanced Parameter Identification of Solar Photovoltaic Models Using a Novel Two-Stage Improved Sea Lion Optimization Algorithm
DOI:
https://doi.org/10.20508/7xhx7v32Keywords:
Photovoltaic Model, Parameter Identification, Metaheuristic Optimization, Sea Lion Optimizer, Two-Stage MethodAbstract
This study introduces a novel two-stage metaheuristic framework for parameter identification (PI) of the single diode model (SDM) in solar cells. The Sea Lion Optimizer (SLO) is, for the first time, applied to SDM parameter estimation and compared with five other classical and recent metaheuristic algorithms. Results demonstrate SLO's superior performance. An improved SLO (ISLO) is then developed, incorporating Lévy flight and personal best information to enhance accuracy. To further improve the accuracy, a two-stage methodology is proposed, using mathematical analysis of the SDM to derive initial parameter estimates and refine search ranges. This approach significantly enhances parameter estimation accuracy and robustness. ISLO shows enhanced accuracy, with an overall RMSE improvement of approximately 59.7 % compared to SLO. The two-stage ISLO further improves estimation, reducing the mean and standard deviation of RMSE by 89.6 % and 91.3 %, respectively. The proposed two-stage methd can also be integrated with other metaheuristic algorithms for similar gains.
Downloads
Downloads
Published
Issue
Section
License
Licensing
All articles published in the Artificial Intelligence Research and Applications, AIRA, are licensed under an open access Creative Commons CC BY 4.0 license, meaning that anyone may download and read the paper for free. In addition, the article may be reused and quoted provided that the original published version is cited. These conditions allow for maximum use and exposure of the work, while ensuring that the authors receive proper credit.
In exceptional circumstances articles may be licensed differently. If you have specific condition (such as one linked to funding) that does not allow this license, please mention this to the editorial office of the journal at submission. Exceptions will be granted at the discretion of the publisher.